Abstract
Bin picking is a highly researched topic, due to the need for automated procedures in industrial environments. A general bin picking system requires a highly structured process, starting with data acquisition, and ending with pose estimation and grasping. A high number of bin picking problems are being presently solved, through deep learning networks, combined with distinct procedures. This study provides a comprehensive review of deep learning approaches, implemented in bin picking problems. Throughout the review are described several approaches and learning methods based on specific domains, such as gripper oriented and object oriented, as well as summarized several methodologies, in order to solve bin picking issues. Furthermore, are introduced current strategies used to simplify particular cases and at last, are presented peculiar means of detecting object poses.

Abstract
Cyber-Physical Systems (CPS) transform traditional systems into a network of connected and heterogeneous systems, integrating computational and physical elements, that works as a complex system whose overall properties are greater than the sum of its parts. However, CPS is not free from faulty episodes and their consequences such as malfunctions, breakdowns, and service interruption. Traditional centralized models for fault-tolerance do not meet the complexity of the current industrial scenarios and particularly the industrial CPS requirements. Having this in mind, this work presents a holonic-based architecture to address the fault-tolerance in CPS by distributing the detection, diagnosis, and recovery in the local individual entities and also considers the emergent behaviour resulting from the collaboration of these entities. An experimental case study is used to illustrate the potential application of the fault-tolerant approach. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Industrial Cyber-Physical Systems (ICPS) deploy a network of connected and heterogeneous systems, integrating computational and physical components, improving production and quality. However, a fault-free system is still utopian, but methodologies related to fault detection and diagnosis are still being treated in isolation or a centralized approach, overlooking the technological advances related to ICPS such as IoT, AI and edge computing. With this in mind, the present work proposes a collaborative architecture for fault detection and diagnosis, regarding the exchange of information for collaborative detection and diagnosis adopting disruptive technologies. Laboratory-scale ICPS experiments were carried out to compare the proposed approach with the approach where each component separately intends to identify and diagnose faults. The results present a faster response generating a system more flexible and robust. © 2022 IEEE.

Abstract
This paper presents a first prototype of an automated system that will be applied in stoneware tableware ceramics finishing, being developed in the scope of STC 4.0 HP project. The main objective of this prototype is to test different alternatives to obtain a precise finish on ceramic pieces produced by GRESTEL - PRODUTOS CERAMICOS S.A, improving the production of irregular pieces that until now are finished using manual labor. This is why the implementation of a closedloop control of the rotation speed of a finishing sponge and its applied force control is proposed. The mechanical structure of the devised solution was prototyped using a FDM based technology. A 3D printer was used for the manufacturing of the structural parts to support the rotating sponge and measurement sensors. In addition a PID based control is used to control the system. Once the prototype has been designed and assembled a series of tests and measurements were carried out leading to the conclusion that the proposed approach is adequate to meet the design requirements for this prototype.

Abstract
The Multi-View Stereo (MVS) is a key process in the photogrammetry workflow. It is responsible for taking the camera's views and finding the maximum number of matches between the images yielding a dense point cloud of the observed scene. Since this process is based on the matching between images it greatly depends on the abil-ity of features matching throughout different images. To improve the matching performance several researchers have proposed the use of Convolutional Neural Networks (CNNs) to solve the MVS problem. Despite the progress in the MVS problem with the usage of CNNs, the Video RAM (VRAM) consumption within these approaches is usually far greater than classical methods, that rely more on RAM, which is cheaper to expand than VRAM. This work then follows the progress made in CasMVSNet in the reduction of GPU memory usage, and further study the changes in the feature extraction process. The Average Group-wise Correlation is used in the cost vol-ume generation, to reduce the number of channels in the cost volume, yielding a reduction in GPU memory usage without noticeable penalties in the result. The deformable convolutions are applied in the feature extraction net -work to augment the spatial sampling locations with learning offsets, without additional supervision, to further improve the network's ability to model transformations. The impact of these changes is measured using quanti-tative and qualitative tests using the DTU and the Tanks and Temples datasets. The modifications reduced the GPU memory usage by 32% and improved the completeness by 9% with a penalty of 6.6% in accuracy on the DTU dataset.(c) 2021 Published by Elsevier B.V.

Abstract
The Agri-Food production requirements needs a more efficient and autonomous processes, and robotics will play a significant role in this process. Deploying agricultural robots on the farm is still a challenging task. Particularly in slope terrains, where it is crucial to avoid obstacles and dangerous steep slope zones. Path planning solutions may fail under several circumstances, as the appearance of a new obstacle. This work proposes a novel open-source solution called AgRobPP-CA to autonomously perform obstacle avoidance during robot navigation. AgRobPP-CA works in real-time for local obstacle avoidance, allowing small deviations, avoiding unexpected obstacles or dangerous steep slope zones, which could impose a fall of the robot. Our results demonstrated that AgRobPP-CA is capable of avoiding obstacles and high slopes in different vineyard scenarios, with low computation requirements. For example, in the last trial, AgRobPP-CA avoided a steep ramp that could impose a fall to the robot.